CASIA OpenIR  > 模式识别国家重点实验室  > 图像与视频分析
Scale-adaptive Deconvolutional Regression Network for Pedestrian Detection
Zhu, Yousong1,2; Wang, Jinqiao1,2; Zhao, Chaoyang1,2; Guo, Haiyun1,2; Lu, Hanqing1,2
2016
Conference NameAsian Conference on Computer Vision
Conference Date2016.11.20-11.24
Conference PlaceTaipei, China
Abstract

Although the Region-based Convolutional Neural Network
(R-CNN) families have shown promising results for object detection,
they still face great challenges for task-specific detection, e.g., pedestrian
detection, the current difficulties of which mainly lie in the large scale
variations of pedestrians and insufficient discriminative power of pedestrian features. To overcome these difficulties, we propose a novel ScaleAdaptive Deconvolutional Regression (SADR) network in this paper.
Specifically, the proposed network can effectively detect pedestrians
of various scales by flexibly choosing which feature layer to regress
object locations according to the height of pedestrians, thus improving
the detection accuracy significantly. Furthermore, considering CNN can
abstract different semantic-level features from different layers, we fuse
features from multiple layers to provide both local characteristics and
global semantic information of the object for final pedestrian classification, which improves the discriminative power of pedestrian features and boosts the detection performance further. Extensive experiments have verified the effectiveness of our proposed approach, which achieves the state-of-the-art log-average miss rate (MR) of 6.94% on the revised Caltech and a competitive result on KITTI.

Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/20146
Collection模式识别国家重点实验室_图像与视频分析
Affiliation1.Institute of Automation, Chinese Academy of Sciences
2.University of Chinese Academy of Sciences
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Zhu, Yousong,Wang, Jinqiao,Zhao, Chaoyang,et al. Scale-adaptive Deconvolutional Regression Network for Pedestrian Detection[C],2016.
Files in This Item: Download All
File Name/Size DocType Version Access License
Zhu Yousong_Scale-ad(625KB)会议论文 开放获取CC BY-NC-SAView Download
Zhu Yousong_Scale-ad(625KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhu, Yousong]'s Articles
[Wang, Jinqiao]'s Articles
[Zhao, Chaoyang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhu, Yousong]'s Articles
[Wang, Jinqiao]'s Articles
[Zhao, Chaoyang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhu, Yousong]'s Articles
[Wang, Jinqiao]'s Articles
[Zhao, Chaoyang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Zhu Yousong_Scale-adaptive Deconvolutional Regression Network for Pedestrian Detection.pdf
Format: Adobe PDF
File name: Zhu Yousong_Scale-adaptive Deconvolutional Regression Network for Pedestrian Detection.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.